追踪治疗中司机的甲基苯丙胺滥用情况：生物力学与动眼特征如何帮助检测高危司机？
Tracing Methamphetamine abuse in under-treatment drivers: How biomechanical and oculomotor features help detect at-risk drivers?
AI总结：
本研究利用驾驶模拟器采集数据，训练KNN模型以90%准确率区分正常司机与甲基苯丙胺滥用史司机，提出借助ADAS技术监测相关参数以降低交通事故风险的主动安全策略。
AI中文摘要：
尽管甲基苯丙胺等兴奋剂影响驾驶的有害影响已得到充分证实，但目前正在接受治疗的个体的驾驶表现却受到的关注少得多。本研究采用驾驶模拟器，比较了有兴奋剂滥用史（处于两个不同治疗阶段）的个体与健康司机对照组的行为。通过眼动仪和Kinect传感器分别持续收集动眼和生物力学数据，这些参数被用于训练K近邻（KNN）分类模型，该模型旨在检测甲基苯丙胺康复中司机的高危行为模式。通过评估各种特征组合和邻域配置，优化后的模型以90%的准确率成功区分了正常司机与有滥用史的司机。通过高级驾驶辅助系统（ADAS）中嵌入的技术持续监测生理和行为参数来检测高危司机，有助于主动安全策略，向司机、乘客及外部监控网络发出实时警报，最终可降低交通事故风险。
英文摘要：
While the detrimental impacts of driving under the influence of stimulants such as methamphetamine are well-documented, the driving performance of individuals currently under-treatment has received considerably less attention. This study compared the behavior of individuals with a history of stimulant abuse (across two distinct treatment phases) with a control group of healthy drivers using a driving simulator. Oculomotor and biomechanical data were continuously collected via an eye-tracker and a Kinect sensor, respectively. These parameters were utilized to train a K-Nearest Neighbors (KNN) classification model designed to detect high-risk behavioral patterns in drivers undergoing methamphetamine rehabilitation. Through the evaluation of various feature combinations and neighborhood configurations, the optimized model successfully discriminated between normal drivers and those with a history of abuse with an accuracy of 90%. Detecting at-risk drivers through technologies embedded in Advanced Driver Assistance Systems (ADAS) by continuously monitoring physiological and behavioral parameters, facilitates a proactive safety strategy. Issuing real-time alerts to the driver, passengers, and external monitoring networks can ultimately mitigate the risk of traffic collisions.
